deepclause-desktop

I also have a strange obsession with Prolog and Markus Triska's article on meta-interpreters heavily inspired me to write a Prolog-based agent framework with a meta-interpreter at its core [0]. I have to admit that writing Prolog sometimes makes me want to bash my my head against the wall, but sometimes the resulting code has a particular kind of beauty that's hard to explain. Anyways, Opus 4.5 is really good at Prolog, so my head feels much better now :-) [0] http://github.com/deepclause/deepclause-desktop

This is a neat idea. The "core motivations" description makes intuitive sense to me. https://github.com/deepclause/deepclause-desktop?tab=readme-... Similarly, I have had some success using Gemini to extract facts from plain text in the format of Souffle Datalog[1] facts. The resulting dataset can then be conveniently and efficiently queried with Datalog. In this way, LLMs allow for a partial return of the software development strategies of the semantic web[2]. I wrote up some thoughts along those lines earlier this year[3]. 1: https://souffle-lang.github.io/ 2: https://en.wikipedia.org/wiki/Semantic_Web 3: https://bjornwestergard.com/llm-extractors/

This looks like a very pragmatic solution, in line with what seems to be going on in the real world [1], where reliability seems to be one of the biggest issues with agentic systems right now. I've been experimenting with a different approach to increase the amount of determinism in such systems: https://github.com/deepclause/deepclause-desktop. It's based on encoding the entire agent behavior in a small and concise DSL built on top of Prolog. While it's not as flexible as a fully fledged agent, it does however, lead to much more reproducible behavior and a more graceful handling of edge-cases. [1] https://arxiv.org/abs/2512.04123

I've been experimenting with giving the LLM a Prolog-based DSL, used in a CodeAct style pattern similar to Huggingface's smolagents. The DSL can be used to orchestrate several tools (MCP or built in) and LLM prompts. It's still very experimental, but a lot of fun to work with. See here: https://github.com/deepclause/deepclause-desktop.

Hi HN, Today I'd like to present the results of my weekend project of the last year or so. Given there are many posts on HN about LLMs and Prolog, I thought that this would be of interest. DeepClause is my own (possibly misguided :-) attempt at combining LLMs with Logic Programming, ultimately hoping to establish a foundation for building more reliable agents, that produce reproducible and fully traceable result. At the heart of DeepClause is a DSL called "DeepClause Meta Language" (DML) which can be used to encode agent behaviors as executable logic programs. DML is executed by a meta-interpreter implemented in Prolog and thus natively supports things like constraint logic programming, knowledge graphs, symbolic reasoning, ... The DML interpreter itself runs inside the SWI Prolog WASM module, thus allowing for a secure and sandboxed exe